pgprof: wrong(?) core counts in "system config"

Running pgprof (various versions <= 14.2) on 48-core node (4 x 12-core AMD) OpenSUSE 11.3, pgprof tells me

  • 9 cores per socket
    5 total cores

in the system configuration tab. Can someone explain what these values mean (the total is < per-socket count)? I was expecting 12 and 48 resp.

I see the same kind of unexpected numbers on other machines / Linux OSes.


Hi Tony,

I’ve been trying unsuccessfully to recreate this behavior here so passed it on to engineering to see if they can. Though, one thought I had is if you were running under a virtual environment or a scheduler (like torque) where you may not have full visibility of the system?

  • Mat

Hi Mat,

this is both on a compute node in a cluster allocated by SLURM (but no virtualization/cpusets etc) and on machines directly ssh’ed into. Screenshot example:
CentOS 5.10, 16 core (2 socket) machine, direct ssh login, trivial omp hello world example.


Also verified on a system where I am just a regular user and didn’t install anything (6 core * 2 socket = 12 core node reports: cores per socket = 4, total cores = 3).

Doesn’t appear to be anything to do with execstack message on

Should note this is for data collected by pgcollect. Using -Mprof gave me the right core/socket count. (Reporting on behalf of someone, so don’t have 100% of the info immediately to hand.)